0 vs 2 benchmarks won
Anthropic Claude 3.5 Haiku | Moonshot AI Kimi K2 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Moonshot AI |
| Release date | Oct 22 2024 | Jul 11 2025 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 1T |
Context window | — | 128k |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 40.6% | 65.8%Best |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 41.6% | 75.1%Best |
| Timeline | ||
| Release gap | Claude 3.5 Haiku shipped 262 days before Kimi K2 | |
Kimi K2 leads Claude 3.5 Haiku on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Claude 3.5 Haiku shipped 262 days before Kimi K2, so benchmark comparisons should account for the intervening progress.
Kimi K2 is an open-source / open-weight model; Claude 3.5 Haiku is proprietary.
On SWE-Bench Verified, Kimi K2 leads at 65.8% vs Claude 3.5 Haiku at 40.6%. On GPQA Diamond, Kimi K2 leads at 75.1% vs Claude 3.5 Haiku at 41.6%.